poly-server 0.1.0__tar.gz

poly_server-0.1.0/.gitignore

@@ -0,0 +1,211 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Node / monorepo
+node_modules/
+*.tsbuildinfo

poly_server-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Victor A. Guerra
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

poly_server-0.1.0/PKG-INFO

@@ -0,0 +1,139 @@
+Metadata-Version: 2.5
+Name: poly-server
+Version: 0.1.0
+Summary: Speech language detection and offline UI translation server for Poly voice-driven interfaces.
+Project-URL: Homepage, https://github.com/VictorAGuerra/Poly-SLID-Interface-Translator
+Project-URL: Repository, https://github.com/VictorAGuerra/Poly-SLID-Interface-Translator
+Project-URL: Issues, https://github.com/VictorAGuerra/Poly-SLID-Interface-Translator/issues
+Author: Victor A. Guerra
+License-Expression: MIT
+License-File: LICENSE
+Keywords: accessibility,i18n,kiosk,language-detection,self-service,speech,translation,whisper
+Classifier: Development Status :: 3 - Alpha
+Classifier: Framework :: FastAPI
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Classifier: Topic :: Software Development :: Internationalization
+Requires-Python: >=3.10
+Requires-Dist: argostranslate>=1.9
+Requires-Dist: fastapi>=0.115
+Requires-Dist: faster-whisper>=1.1
+Requires-Dist: numpy>=1.24
+Requires-Dist: uvicorn[standard]>=0.30
+Requires-Dist: webrtcvad-wheels>=2.0.14
+Provides-Extra: dev
+Requires-Dist: httpx>=0.27; extra == 'dev'
+Requires-Dist: pytest>=8; extra == 'dev'
+Provides-Extra: mic
+Requires-Dist: sounddevice>=0.5; extra == 'mic'
+Description-Content-Type: text/markdown
+
+# poly-server
+
+**English** · [Português](#português)
+
+Speech language detection and offline UI translation server for
+[Poly](https://www.npmjs.com/package/@swalay/poly-react), voice-driven
+interfaces for self-service kiosks.
+
+- **Speech → language** with [faster-whisper](https://github.com/SYSTRAN/faster-whisper).
+- **UI translation** with [Argos Translate](https://github.com/argosopentech/argos-translate),
+  fully offline, with an English pivot when there's no direct language pair
+  and a persistent SQLite cache.
+- **Two audio modes:** the server's own microphone (kiosk: screen and server on
+  the same machine) or audio streamed from the browser.
+- Nothing leaves the device: no cloud APIs.
+
+## Install
+
+```bash
+# CPU-only PyTorch first (Argos needs it); avoids ~3 GB of CUDA libraries
+pip install torch --index-url https://download.pytorch.org/whl/cpu
+pip install "poly-server[mic]"
+```
+
+The `mic` extra enables local microphone capture (needs PortAudio:
+`sudo apt install libportaudio2` on Debian/Ubuntu). Skip it if audio only
+comes from the browser.
+
+## Run
+
+```bash
+poly-server serve                     # http://127.0.0.1:8000, local microphone
+poly-server serve --no-mic            # browser audio only
+poly-server devices                   # list microphones
+poly-server serve --mic-device 2
+```
+
+### Offline kiosks
+
+Download everything once during installation, then run without network:
+
+```bash
+poly-server download --base en --languages pt,es,fr,ar,ja,zh
+poly-server serve --offline
+```
+
+## Configuration
+
+Every option can be set with a `POLY_*` environment variable:
+
+| Variable | Default | |
+| --- | --- | --- |
+| `POLY_HOST` / `POLY_PORT` | `127.0.0.1` / `8000` | |
+| `POLY_CORS_ORIGINS` | `*` | Comma-separated allowed origins. |
+| `POLY_MIC` | `true` | Capture the local microphone. |
+| `POLY_MIC_DEVICE` | system default | Input device index or name. |
+| `POLY_WHISPER_MODEL` | `base` | `tiny`, `base`, `small`, `medium`, `large-v3`. |
+| `POLY_WHISPER_DEVICE` | `auto` | `cpu`, `cuda`, `auto`. |
+| `POLY_WHISPER_COMPUTE_TYPE` | `int8` | |
+| `POLY_VAD_MODE` | `2` | 0 (lenient) to 3 (aggressive) voice detection. |
+| `POLY_END_TRIGGER_MS` | `600` | Silence that ends an utterance. |
+| `POLY_MAX_UTTERANCE_SEC` | `12` | |
+| `POLY_CACHE_DIR` | `~/.cache/poly-server` | Models and translation cache. |
+| `POLY_AUTO_DOWNLOAD` | `true` | Download translation packages on demand. |
+
+## API
+
+| Endpoint | |
+| --- | --- |
+| `GET /health` | `{ ok, version, mic }` |
+| `POST /i18n/auto-translate` | `{ source_lang, target_lang, texts: { key: text } }` → `{ target_lang, texts }`. Returns `422` with `code: "unsupported_language_pair"` when no translation exists. |
+| `WS /ws` | Recognition events from the local microphone, broadcast to every client. Send `{"type":"config","listening":"manual"}` to listen only on demand, then `{"type":"listen","action":"start"\|"stop"}`; the server replies with `{"type":"listening","listening":bool}` and `{"type":"speech_start"}`. |
+| `WS /ws/audio` | Send binary PCM16 LE mono 16 kHz; receive `{"type":"speech_start"}` / `{"type":"utterance_end"}` as speech starts and ends, then the recognition event. Text messages: `{"type":"flush"}` recognizes the speech in progress, `{"type":"reset"}` discards it. |
+
+Event: `{ "type": "asr", "language": "pt", "confidence": 0.97, "text": "...", "latency_sec": 1.4 }`
+
+### Embedding
+
+```python
+from poly_server import Settings, create_app
+
+app = create_app(Settings(mic=False, whisper_model="small"))
+```
+
+`create_app` also accepts custom `recognizer` and `translator` objects, to plug
+in another speech model or translation service.
+
+## License
+
+MIT
+
+---
+
+## Português
+
+Servidor de detecção do idioma falado e tradução offline de interfaces para o
+Poly.
+
+- **Fala → idioma** com faster-whisper.
+- **Tradução** com Argos Translate, 100% offline, passando pelo inglês quando
+  não há pacote direto entre dois idiomas, e com cache em disco (SQLite).
+- **Dois modos de áudio:** o microfone do próprio servidor (quiosque) ou o
+  áudio enviado pelo navegador.
+- Nada sai do aparelho: nenhuma API na nuvem.
+
+Instalação, execução e configuração: veja os comandos acima. Para quiosques
+sem internet, rode `poly-server download` na instalação e depois
+`poly-server serve --offline`.

poly_server-0.1.0/README.md

@@ -0,0 +1,108 @@
+# poly-server
+
+**English** · [Português](#português)
+
+Speech language detection and offline UI translation server for
+[Poly](https://www.npmjs.com/package/@swalay/poly-react), voice-driven
+interfaces for self-service kiosks.
+
+- **Speech → language** with [faster-whisper](https://github.com/SYSTRAN/faster-whisper).
+- **UI translation** with [Argos Translate](https://github.com/argosopentech/argos-translate),
+  fully offline, with an English pivot when there's no direct language pair
+  and a persistent SQLite cache.
+- **Two audio modes:** the server's own microphone (kiosk: screen and server on
+  the same machine) or audio streamed from the browser.
+- Nothing leaves the device: no cloud APIs.
+
+## Install
+
+```bash
+# CPU-only PyTorch first (Argos needs it); avoids ~3 GB of CUDA libraries
+pip install torch --index-url https://download.pytorch.org/whl/cpu
+pip install "poly-server[mic]"
+```
+
+The `mic` extra enables local microphone capture (needs PortAudio:
+`sudo apt install libportaudio2` on Debian/Ubuntu). Skip it if audio only
+comes from the browser.
+
+## Run
+
+```bash
+poly-server serve                     # http://127.0.0.1:8000, local microphone
+poly-server serve --no-mic            # browser audio only
+poly-server devices                   # list microphones
+poly-server serve --mic-device 2
+```
+
+### Offline kiosks
+
+Download everything once during installation, then run without network:
+
+```bash
+poly-server download --base en --languages pt,es,fr,ar,ja,zh
+poly-server serve --offline
+```
+
+## Configuration
+
+Every option can be set with a `POLY_*` environment variable:
+
+| Variable | Default | |
+| --- | --- | --- |
+| `POLY_HOST` / `POLY_PORT` | `127.0.0.1` / `8000` | |
+| `POLY_CORS_ORIGINS` | `*` | Comma-separated allowed origins. |
+| `POLY_MIC` | `true` | Capture the local microphone. |
+| `POLY_MIC_DEVICE` | system default | Input device index or name. |
+| `POLY_WHISPER_MODEL` | `base` | `tiny`, `base`, `small`, `medium`, `large-v3`. |
+| `POLY_WHISPER_DEVICE` | `auto` | `cpu`, `cuda`, `auto`. |
+| `POLY_WHISPER_COMPUTE_TYPE` | `int8` | |
+| `POLY_VAD_MODE` | `2` | 0 (lenient) to 3 (aggressive) voice detection. |
+| `POLY_END_TRIGGER_MS` | `600` | Silence that ends an utterance. |
+| `POLY_MAX_UTTERANCE_SEC` | `12` | |
+| `POLY_CACHE_DIR` | `~/.cache/poly-server` | Models and translation cache. |
+| `POLY_AUTO_DOWNLOAD` | `true` | Download translation packages on demand. |
+
+## API
+
+| Endpoint | |
+| --- | --- |
+| `GET /health` | `{ ok, version, mic }` |
+| `POST /i18n/auto-translate` | `{ source_lang, target_lang, texts: { key: text } }` → `{ target_lang, texts }`. Returns `422` with `code: "unsupported_language_pair"` when no translation exists. |
+| `WS /ws` | Recognition events from the local microphone, broadcast to every client. Send `{"type":"config","listening":"manual"}` to listen only on demand, then `{"type":"listen","action":"start"\|"stop"}`; the server replies with `{"type":"listening","listening":bool}` and `{"type":"speech_start"}`. |
+| `WS /ws/audio` | Send binary PCM16 LE mono 16 kHz; receive `{"type":"speech_start"}` / `{"type":"utterance_end"}` as speech starts and ends, then the recognition event. Text messages: `{"type":"flush"}` recognizes the speech in progress, `{"type":"reset"}` discards it. |
+
+Event: `{ "type": "asr", "language": "pt", "confidence": 0.97, "text": "...", "latency_sec": 1.4 }`
+
+### Embedding
+
+```python
+from poly_server import Settings, create_app
+
+app = create_app(Settings(mic=False, whisper_model="small"))
+```
+
+`create_app` also accepts custom `recognizer` and `translator` objects, to plug
+in another speech model or translation service.
+
+## License
+
+MIT
+
+---
+
+## Português
+
+Servidor de detecção do idioma falado e tradução offline de interfaces para o
+Poly.
+
+- **Fala → idioma** com faster-whisper.
+- **Tradução** com Argos Translate, 100% offline, passando pelo inglês quando
+  não há pacote direto entre dois idiomas, e com cache em disco (SQLite).
+- **Dois modos de áudio:** o microfone do próprio servidor (quiosque) ou o
+  áudio enviado pelo navegador.
+- Nada sai do aparelho: nenhuma API na nuvem.
+
+Instalação, execução e configuração: veja os comandos acima. Para quiosques
+sem internet, rode `poly-server download` na instalação e depois
+`poly-server serve --offline`.

poly_server-0.1.0/pyproject.toml

@@ -0,0 +1,50 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "poly-server"
+version = "0.1.0"
+description = "Speech language detection and offline UI translation server for Poly voice-driven interfaces."
+readme = "README.md"
+license = "MIT"
+license-files = ["LICENSE"]
+requires-python = ">=3.10"
+authors = [{ name = "Victor A. Guerra" }]
+keywords = ["i18n", "translation", "speech", "language-detection", "whisper", "kiosk", "self-service", "accessibility"]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Framework :: FastAPI",
+  "Intended Audience :: Developers",
+  "Programming Language :: Python :: 3",
+  "Topic :: Multimedia :: Sound/Audio :: Speech",
+  "Topic :: Software Development :: Internationalization",
+]
+dependencies = [
+  "fastapi>=0.115",
+  "uvicorn[standard]>=0.30",
+  "faster-whisper>=1.1",
+  "argostranslate>=1.9",
+  "webrtcvad-wheels>=2.0.14",
+  "numpy>=1.24",
+]
+
+[project.optional-dependencies]
+mic = ["sounddevice>=0.5"]
+dev = ["pytest>=8", "httpx>=0.27"]
+
+[project.scripts]
+poly-server = "poly_server.cli:main"
+
+[project.urls]
+Homepage = "https://github.com/VictorAGuerra/Poly-SLID-Interface-Translator"
+Repository = "https://github.com/VictorAGuerra/Poly-SLID-Interface-Translator"
+Issues = "https://github.com/VictorAGuerra/Poly-SLID-Interface-Translator/issues"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/poly_server"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+markers = ["integration: loads real models (slow, needs network on first run)"]
+addopts = "-m 'not integration'"

poly_server-0.1.0/src/poly_server/__init__.py

@@ -0,0 +1,8 @@
+"""poly-server: detecção do idioma falado e tradução de interfaces para o Poly."""
+
+__version__ = "0.1.0"
+
+from .app import create_app
+from .config import Settings
+
+__all__ = ["create_app", "Settings", "__version__"]

poly_server-0.1.0/src/poly_server/__main__.py

@@ -0,0 +1,3 @@
+from .cli import main
+
+main()